A machine learning approach for the detection of supporting rock bolts from laser scan data in an underground mine
- Submitting institution
-
University of Exeter
- Unit of assessment
- 12 - Engineering
- Output identifier
- 6017
- Type
- D - Journal article
- DOI
-
10.1016/j.tust.2020.103656
- Title of journal
- Tunnelling and Underground Space Technology
- Article number
- ARTN 103656
- First page
- -
- Volume
- 107
- Issue
- -
- ISSN
- 0886-7798
- Open access status
- Compliant
- Month of publication
- October
- Year of publication
- 2020
- URL
-
-
- Supplementary information
-
-
- Request cross-referral to
- -
- Output has been delayed by COVID-19
- No
- COVID-19 affected output statement
- -
- Forensic science
- No
- Criminology
- No
- Interdisciplinary
- No
- Number of additional authors
-
2
- Research group(s)
-
H - CSM
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- This paper describes integration of point cloud data and deep learning algorithms to automatically identify rock bolts for improved safety and quality control of bolting support systems in an underground environment. The research was undertaken in collaboration with Sandvik Mining Construction and is being explored for product development on their future underground equipment (Jussi Puura, Sandvik Research, Technology and Digitalisation Lead: jussi.puura@sandvik.com). The underlying research presented in the paper informed development of the ERDF-funded Immersive Business (112813; €643k) and Innovate UK-funded Autonomous Robotic InSpEction (ARISE: 105607; £175k) projects.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -